© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 29093
    Prev
    Next
    INDEX
    Explanations

    lexical items that include the suffix "-est" or similar variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    keit
    -0.08
    lett
    -0.07
    UED
    -0.07
    екÑģи
    -0.07
    uetooth
    -0.07
    iddet
    -0.07
    ré
    -0.07
    beits
    -0.07
     liberalism
    -0.07
    ksam
    -0.07
    POSITIVE LOGITS
    hetics
    0.10
    ee
    0.08
    ech
    0.08
    rian
    0.08
    rial
    0.08
    ea
    0.08
    ablish
    0.07
    aurants
    0.07
    aurant
    0.07
    andard
    0.07
    Activations Density 0.018%

    No Known Activations